Least-to-Most Prompting
Decompose the hard problem into easy sub-problems, solve them in order.
Intent & Description
🎯 Intent
Guide the model through progressive problem decomposition — easiest sub-problem first, hardest last — so each step scaffolds the next.
📋 Context
LLMs struggle with problems that require holding many intermediate results simultaneously. CoT helps, but asking the model to decompose and solve in one shot is still brittle for complex tasks. Least-to-Most separates decomposition from solving, and solves sub-problems sequentially so earlier answers inform later ones.
💡 Solution
Two-stage prompt flow — (1) Decomposition prompt: ask the model to break the problem into ordered sub-questions from simplest to hardest. (2) Sequential solving: feed each sub-question with its predecessors’ answers in context, building a chain of grounded intermediate results until the final question is answered. See also: chain-of-thought, goal-decomposition, query-decomposition-agent.
Real-world Use Case
- Multi-hop reasoning tasks (QA requiring several inference steps).
- Math word problems with multiple operations.
- Any task where the answer to part A is required to correctly answer part B.
Source
📌 TL;DR
Split the problem smallest-first, solve in order — each answer scaffolds the next.
Advantages
- Measurably outperforms standard CoT on compositional tasks.
- Decomposition step surfaces hidden complexity before it causes failures.
- Sub-problem answers are individually checkable — great for debugging.
Disadvantages
- Requires multiple LLM calls — latency and cost scales with decomposition depth.
- Decomposition quality is critical; a bad split produces wrong sub-problems.
- Sequential dependency means no parallelism — each step waits on the last.